Clustering-based Sequential Feature Selection Approach for High Dimensional Data Classification.
M. AlimoussaAlice PorebskiNicolas VandenbrouckeRachid Oulad Haj ThamiSanaa El FkihiPublished in: VISIGRAPP (4: VISAPP) (2021)
Keyphrases
- high dimensional data
- high dimensionality
- feature selection
- dimensionality reduction
- dimension reduction
- high dimensional
- small sample size
- nearest neighbor
- low dimensional
- classification accuracy
- regression problems
- feature space
- similarity search
- gene expression data
- support vector
- subspace clustering
- text classification
- high dimensions
- feature extraction
- feature selection algorithms
- pattern recognition
- input space
- manifold learning
- data sets
- nonlinear dimensionality reduction
- data analysis
- text categorization
- high dimensional spaces
- feature set
- support vector machine
- machine learning
- linear discriminant analysis
- data points
- clustering high dimensional data
- lower dimensional
- high dimensional feature spaces
- neural network
- decision trees
- variable selection
- missing values
- cross validation
- high dimensional datasets
- principal component analysis
- feature vectors
- classification algorithm
- dimensional data
- unsupervised learning
- model selection
- underlying manifold
- variable weighting
- multivariate temporal data